Learning One Representation to Optimize All Rewards.
Ahmed TouatiYann OllivierPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- learning systems
- incremental learning
- prior knowledge
- learning problems
- image representation
- knowledge representation
- multiple representations
- feature representation
- learning community
- inductive learning
- learning tasks
- unsupervised learning
- online learning
- database
- active learning
- object recognition
- learning environment
- training data
- data mining
- real time